Beyond weight plasticity: Local learning with propagation delays in spiking neural networks

Jørgen Jensen Farner, Ola Huse Ramstad, Stefano Nichele, Kristine Heiney

Keywords: delay plasticity, local learning, spiking neural networks, Izhikevich neuron, generalized learning

TL;DR: We developed an activity-dependent delay plasticity algorithm to train spiking neural networks using time encoding, and we show that networks trained with this method can generalize their training to unseen input classes.

Abstract: We propose a novel local learning rule for spiking neural networks in which spike propagation times undergo activity-dependent plasticity. Our plasticity rule aligns pre-synaptic spike times to produce a stronger and more rapid response. Inputs are encoded by latency coding and outputs decoded by matching similar patterns of output spiking activity. We demonstrate the use of this method in a three-layer feedfoward network with inputs from a database of handwritten digits. Networks consistently showed improved classification accuracy after training, and training with this method also allowed networks to generalize to an input class unseen during training. Our proposed method takes advantage of the ability of spiking neurons to support many different time-locked sequences of spikes, each of which can be activated by different input activations. The proof-of-concept shown here demonstrates the great potential for local delay learning to expand the memory capacity and generalizability of spiking neural networks.

Submission Number: 6